Enabling technology for recognition of individual salmon by using computer vision and machine learning algorithms.
The goal for the INDISAL-project is to enable technology for identification of individual salmon in industrial sea based salmon farming. Based on the insight that Atlantic salmon maintain a unique spot pattern after they are moved from the hatchery to salt water, identification will be done by using the melanophore spot-pattern in the head region as a biometric fingerprint.
Innovative underwater light and camera solutions are developed and improved in order to receive high quality underwater video recordings. These allow computer vision and machine learning techniques to automatically identify individual fish and measure welfare indicators like growth, stress levels and physical damages on an individual level.
The innovation enables the salmon farming industry to have an overview of the current state of each individual salmon, while the collected time-line data of individual salmons can be used to analyze in detail which operational events had an impact on both individual fish and the whole fish-population.